Abstract
Abstract. 3D point clouds are robust representations of real-world objects and usually contain information about the shape, size, position and radiometry of the scene. However, unstructured point clouds do not directly exploit the full potential of such information and thus, further analysis is commonly required. Especially when dealing with cultural heritage objects which are, typically, described by complex 3D geometries, semantic segmentation is a fundamental step for the automatic identification of shapes, erosions, etc. This paper focuses on the efficient extraction of semantic classes that would support the generation of geometric primitives such as planes, spheres, cylinders, etc. Our semantic segmentation approach relies on supervised learning using a Random Forest algorithm, while the geometric shapes are identified and extracted with the RANSAC model fitting algorithm. In this way the parametric modelling procedure in a HBIM environment is easily enabled. Our experiments show the efficient label transferability of our 3D semantic segmentation approach across different Doric Greek temples, with qualitatively and quantitatively evaluations.
Highlights
Data acquisition techniques such as photogrammetry and laser scanning commonly generate 3D point clouds to describe the surface of a real-world object or a scene
Higher-level semantic information is crucial towards scene understanding and analysis and, semantic segmentation has become a powerful tool for 2D (Marmanis et al, 2016; Chen et al, 2018; Kirillov et al, 2019) as well as 3D (Blaha et al, 2016; Armenti et al, 2017; Stathopoulou et al, 2021) data analysis
In the cultural heritage domain, the use of Historic Building Information Modelling (HBIM) has become a research topic of great interest as it is able to model the state of complex historic structures throughout their life cycle by deconstructing and analysing their different components and details, and several studies have worked towards this scope (Barazzetti, 2016; Murtiyoso and Grussenmayer, 2019; Yang et al, 2020a)
Summary
Data acquisition techniques such as photogrammetry and laser scanning commonly generate 3D point clouds to describe the surface of a real-world object or a scene Such representations are mathematically expressed by matrices of unorganised points; the rows of these matrices correspond to the total number of points contained in the 3D cloud and the columns contain point-level information such as coordinates, normal direction, colour, intensity etc. This kind of data can be sufficient for general 3D recording purposes, yet it does not provide any semantically meaningful attribute of the scene as such. HBIM could act as a multi-dimensional tool and process essential for the management, preservation, restoration and dissemination of cultural heritage
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
